A workshop about survey data analysis will be held on the occasion of the 9th German Stata Users' Group Meeting on June 30th 2011 in Bamberg.

More information about the Workshop is given below. For more information about the German Stata Users' Group meeting see http://www.stata.com/meeting/germany11/

Overview ---------

Survey data analysis using Stata by Jeffrey Pitblado

June 30th 2011

University of Bamberg Feldkirchenstraße 21 96045 Bamberg Germany

Fees and Registration ---------------------

You can enroll by emailing Anke Mrosek (anke.mrosek@dpc.de) or by writing, phoning, or faxing to

Anke Mrosek Dittrich & Partner Consulting GmbH Kieler Str. 17 42697 Solingen Telephone: +49 (0) 212 260 6624 Fax: +49 (0) 212 260 6666

German Users' Group meeting: 40 Euro (students 20 Euro) Workshop only: 90 Euro Workshop and Users' meeting: 100 Euro

Description ------------

This workshop covers how to use Stata for survey data analysis assuming a fixed population. Knowledge of Stata is not required, but attendees are assumed to have some statistical knowledge, such as what is typically covered in an introductory statistics course. We will begin by reviewing the sampling methods used to collect survey data, and how they affect the estimation of totals,ratios, and regression coefficients. We will then cover the three variance estimators implemented in Stata's survey estimation commands. Strata with a single sampling unit, certainty sampling units, subpopulation estimation, and poststratification will be also covered in some detail. Each topic will be illustraited with an example in a Stata session.

Outline ---------

1. Sampling design characteristics - cluster sampling - stratified sampling - sampling without replacement 2. Variance estimation - linearization - balanced repeated replication (BRR) - jackknife 3. Special types of sampling units - Strata with a single sampling unit - Certainty units

4. Restricted sample and subpopulation estimation

5. Postratification

Learning outcomes -----------------

Attendees of this workshop will walk away with the following knowledge.

1. The difference between Stata's standard estimation commands and svy estimation commands.

2. How to use Stata's -svyset- command to identify the survey characteristics present in the dataset. These characteristics include: ­ - sampling units at each sampling stage ­ - strata at each sampling stage ­ - sampling fractions used in the finite population correction when units are sampled without replacement at each sampling stage ­ - replication weight variables ­ - poststrata and their associated sizes

3. How to handle certainty units.

4. The available choices for handling strata with one sampling unit.

5. The difference between restricted sample estimation and subpopulation estimation.

Instructional methods ---------------------

This workshop will combine slides, (using the LaTeX beamer class) for displaying methods and formulas, with an interactive Stata session.

Presenter background ---------------------

Jeff Pitblado is Associate Director, Statistical Software at StataCorp LP. He is responsible for the survey features in Stata. Starting with Stata 9, he has added the following survey features to Stata: the -svy- prefix, the -svy brr- prefix, the -svy jackknife- prefix, multistage design settings in the -svyset- command, linearized variance estimation for multistage designs, poststratification, and direct standardization of means, proportions, and ratios. He also added survey features to Stata's -ml- command and is a coauthor of "Maximum Likelihood Estimation with Stata" (second, third, and fourth editions). Jeff earned a Ph.D. in Mathematical Statistics from Southern Methodist University in 2000.